X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911593377300480 |
|---|---|
| author | Pace, Maximus A. Dan, Prithwish Ning, Chuanruo Bhardwaj, Atiksh Du, Audrey Duan, Edward W. Ma, Wei-Chiu Kedia, Kushal |
| author_facet | Pace, Maximus A. Dan, Prithwish Ning, Chuanruo Bhardwaj, Atiksh Du, Audrey Duan, Edward W. Ma, Wei-Chiu Kedia, Kushal |
| contents | Human videos are a scalable source of training data for robot learning. However, humans and robots significantly differ in embodiment, making many human actions infeasible for direct execution on a robot. Still, these demonstrations convey rich object-interaction cues and task intent. Our goal is to learn from this coarse guidance without transferring embodiment-specific, infeasible execution strategies. Recent advances in generative modeling tackle a related problem of learning from low-quality data. In particular, Ambient Diffusion is a recent method for diffusion modeling that incorporates low-quality data only at high-noise timesteps of the forward diffusion process. Our key insight is to view human actions as noisy counterparts of robot actions. As noise increases along the forward diffusion process, embodiment-specific differences fade away while task-relevant guidance is preserved. Based on these observations, we present X-Diffusion, a cross-embodiment learning framework based on Ambient Diffusion that selectively trains diffusion policies on noised human actions. This enables effective use of easy-to-collect human videos without sacrificing robot feasibility. Across five real-world manipulation tasks, we show that X-Diffusion improves average success rates by 16% over naive co-training and manual data filtering. The project website is available at https://portal-cornell.github.io/X-Diffusion/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_04671 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations Pace, Maximus A. Dan, Prithwish Ning, Chuanruo Bhardwaj, Atiksh Du, Audrey Duan, Edward W. Ma, Wei-Chiu Kedia, Kushal Robotics Artificial Intelligence Computer Vision and Pattern Recognition Human videos are a scalable source of training data for robot learning. However, humans and robots significantly differ in embodiment, making many human actions infeasible for direct execution on a robot. Still, these demonstrations convey rich object-interaction cues and task intent. Our goal is to learn from this coarse guidance without transferring embodiment-specific, infeasible execution strategies. Recent advances in generative modeling tackle a related problem of learning from low-quality data. In particular, Ambient Diffusion is a recent method for diffusion modeling that incorporates low-quality data only at high-noise timesteps of the forward diffusion process. Our key insight is to view human actions as noisy counterparts of robot actions. As noise increases along the forward diffusion process, embodiment-specific differences fade away while task-relevant guidance is preserved. Based on these observations, we present X-Diffusion, a cross-embodiment learning framework based on Ambient Diffusion that selectively trains diffusion policies on noised human actions. This enables effective use of easy-to-collect human videos without sacrificing robot feasibility. Across five real-world manipulation tasks, we show that X-Diffusion improves average success rates by 16% over naive co-training and manual data filtering. The project website is available at https://portal-cornell.github.io/X-Diffusion/. |
| title | X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.04671 |